© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10701
    Prev
    Next
    INDEX
    Explanations

    expressions indicating commitment or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences that begin with "This."

    np_acts-logits-general · gemini-2.0-flash

    This is followed by a noun or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.36
    arriver
    -0.35
     elet
    -0.33
    esercito
    -0.32
    Soorten
    -0.32
    CloseOperation
    -0.31
     arrivée
    -0.30
    glement
    -0.30
    AndEndTag
    -0.29
     Fotografía
    -0.29
    POSITIVE LOGITS
    :✨
    1.10
    tagHelperRunner
    0.81
     betweenstory
    0.71
     [*]
    0.69
    󠁴
    0.68
    reportWebVitals
    0.68
    NameInMap
    0.66
     pinulongan
    0.61
     للاسماء
    0.61
    DockStyle
    0.61
    Activations Density 0.246%

    No Known Activations